Learning form data is investigated as minimization of empirical error functional in spaces of continuous functions and spaces defined by kernels. Using methods from theory of inverse problems, an alternative proof of Representer Theorem is given. Regularized and non regularized minimization of empirical error is compared. © 2012 Springer-Verlag GmbH Berlin Heidelberg.
CITATION STYLE
Kůrková, V. (2012). Learning from data as an optimization and inverse problem. In Studies in Computational Intelligence (Vol. 399, pp. 361–372). https://doi.org/10.1007/978-3-642-27534-0_24
Mendeley helps you to discover research relevant for your work.